• Ritunsa Mishra
• Rabinarayan Satpathy
• Bibudhendu Pati
• Dibyanshu Mohapatra

Aim of the Work- This study aims to improve disease classification accuracy using machine learning models on electronic health records (EHRs). By comparing Ran-dom Forest, XGBoost, and Gradient Boosting, the research seeks to determine the most effective algorithm for reliable disease prediction, aiding healthcare practition-ers in model selection. Methods- A comprehensive dataset covering various medical conditions was pre-processed to ensure data consistency and eliminate noise. Feature engineering was applied to extract relevant information. Random Forest, XGBoost, and Gradient Boosting models were then trained on this refined dataset. Cross-validation methods were used to ensure robustness and generalizability. Results- The models were assessed using accuracy, precision, recall, and F1 score. Random Forest achieved the highest accuracy at 77.63%, outperforming XGBoost and Gradient Boosting. Comparative analysis provided insights into the strengths and weaknesses of each algorithm. Conclusion- The study highlights significant improvements in disease classification accuracy with optimized predictive models. Random Forest's accuracy of 77.63% demonstrates its potential for effective use of EHRs in clinical decision-making. This research supports the integration of advanced technologies into healthcare to im-prove patient outcomes and resource utilization.

"OPTIMIZING PATIENT DISEASE CLASSIFICATION USING ELECTRONIC HEALTH RECORDS THROUGH MACHINE LEARNING BASED PREDICTIVE MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 10, page no.g380-g389, October-2024, Available :http://www.jetir.org/papers/JETIR2410646.pdf

"OPTIMIZING PATIENT DISEASE CLASSIFICATION USING ELECTRONIC HEALTH RECORDS THROUGH MACHINE LEARNING BASED PREDICTIVE MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 10, page no. ppg380-g389, October-2024, Available at : http://www.jetir.org/papers/JETIR2410646.pdf